Sökning: id:"swepub:oai:lup.lub.lu.se:e40ec581-1249-4263-9b7a-2113427f6f05" >
Keyword Transformer...
Keyword Transformer: A Self-Attention Model for Keyword Spotting
-
- Berg, Axel (författare)
- Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH
-
O'Connor, Mark (författare)
-
Cruz, Miguel Tairum (författare)
-
(creator_code:org_t)
- 2021
- 2021
- Engelska 5 s.
-
Ingår i: Proc. Interspeech 2021. ; , s. 4249-4253
- Relaterad länk:
-
https://arxiv.org/ab... (free)
-
visa fler...
-
http://dx.doi.org/10... (free)
-
https://lup.lub.lu.s...
-
https://doi.org/10.2...
-
visa färre...
Abstract
Ämnesord
Stäng
- The Transformer architecture has been successful across many domains, including natural language processing, computer vision and speech recognition. In keyword spotting, self-attention has primarily been used on top of convolutional or recurrent encoders. We investigate a range of ways to adapt the Transformer architecture to keyword spotting and introduce the Keyword Transformer (KWT), a fully self-attentional architecture that exceeds state-of-the-art performance across multiple tasks without any pre-training or additional data. Surprisingly, this simple architecture outperforms more complex models that mix convolutional, recurrent and attentive layers. KWT can be used as a drop-in replacement for these models, setting two new benchmark records on the Google Speech Commands dataset with 98.6% and 97.7% accuracy on the 12 and 35-command tasks respectively.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Signalbehandling (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Signal Processing (hsv//eng)
- NATURVETENSKAP -- Matematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics (hsv//eng)
Nyckelord
- keyword spotting
- machine learning
- machine learning
- keyword spotting
- transformer
- speech recognition
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)